Unbounded External Image Fetch in Validation Leads to Resource-Exhaustion DoS in huggingface/text-generation-inference
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- None
- Attack complexity
- Low
- Impact type
- Denial of service
- Confidentiality · integrity · availability
- None · None · High
- Fix status
- Fixed
Attack profile from CVSS 3.0 · CNA. Fix status from CNA and GitHub. Impact type from CWE-400.
Summary
A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET request, reading the entire response body into memory and cloning it before decoding. This behavior can lead to resource exhaustion, including network bandwidth saturation, memory inflation, and CPU overutilization. The vulnerability is triggered even if the request is later rejected for exceeding token limits. The default deployment configuration, which lacks memory usage limits and authentication, exacerbates the impact, potentially crashing the host machine. The issue is resolved in version 3.3.7.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- Poc
- Automatable
- Yes
- Technical impact
- Partial
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| huggingface | huggingface/text-generation-inference | before 3.3.7 | 3.3.7 | Patch available | CNA |
| — | text-generation (PyPI) | before 3.3.7 | 3.3.7 | Patch available | GHSA-j7x9-7j54-2v3h |
- huggingface/text-generation-inference Vendorhuggingface Affected before 3.3.7 Fixed in 3.3.7 Patch available CNA
- text-generation (PyPI) Vendor— Affected before 3.3.7 Fixed in 3.3.7 Patch available GHSA-j7x9-7j54-2v3h
Remediation
- Fix · CNA huggingface/text-generation-inference (huggingface) Fixed in 3.3.7
- Fix · GHSA-j7x9-7j54-2v3h text-generation (PyPI) Fixed in 3.3.7 Advisory →
Timeline
- 2026-10-02 Threatist record created from CVE-2026-0599
- 2026-10-03 Alias added: GHSA-j7x9-7j54-2v3h
References
More huggingface vulnerabilities
- TI-2026-48351 sentence-transformers Arbitrary Code Execution on Local Model Load Despite trust_remote_code=False CVSS 4.0CRITICAL 9.3
- TI-2026-20914 LeRobot Unsafe Deserialization Remote Code Execution via gRPC CVSS 4.0CRITICAL 9.3
- TI-2026-04577 Policy Bypass in LightGlue Nested Config Resolution in huggingface/transformers CVSS 3.1CRITICAL 9.6
- TI-2025-04589 Sandbox Escape Vulnerability in huggingface/smolagents CVSS 3.1CRITICAL 10.0
- TI-2026-79938 Pickle deserialization in Hugging Face Datasets allows code execution CVSS 4.0HIGH 8.7
- TI-2026-32710 Diffusers: None.py Trust Remote Code Bypass CVSS 3.1HIGH 8.8
Sources
- CVE-2026-0599 · CVE Program
- CVE-2026-0599 · NVD
- FIRST EPSS
- GHSA-j7x9-7j54-2v3h · GitHub Advisory Database · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences